INDEX

Explanations

negations or phrases indicating something is not typical or expected

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

omatic

-0.08

bard

-0.07

urd

-0.07

âĻ¡

-0.06

inos

-0.06

 ÂłÂł ÂłÂł

-0.06

ÑĨÐµÐ¼

-0.06

irler

-0.06

Ð³Ð¾Ð²

-0.06

ÑĤÑı

-0.06

POSITIVE LOGITS

 merely

0.14

 another

0.13

 simply

0.12

 mere

0.12

another

0.10

mere

0.10

 just

0.09

 Another

0.09

 typical

0.09

 like

0.09

Activations Density 0.030%